MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunctionresolve_inference_model
( body_model: object, settings: Mapping[str, object], cli_model: str | None, endpoint_model: o
litellm/proxy/common_utils/http_parsing_utils.py:63
↓ 8 callersFunctionresolve_observation_id
Map a caller's parent observation id onto v4's 16 lowercase hex characters.
litellm/integrations/langfuse/langfuse_sdk.py:150
↓ 8 callersMethodresolve_openapi_upstream_auth
Resolve the gateway-owned upstream credential for a spec_path (OpenAPI) tool call. OpenAPI tools egress through a plain httpx call assembled
litellm/proxy/mcp_server/mcp_server_manager.py:6981
↓ 8 callersFunctionresolve_operation_params
Return a copy of *operation* with fully-resolved, merged parameters. Handles two common patterns in real-world OpenAPI specs: 1. **$ref para
litellm/proxy/mcp_server/openapi_to_mcp_generator.py:409
↓ 8 callersFunctionresolve_pass_through_request_timeout
Resolve the upstream httpx timeout for pass_through_request. Precedence: per-endpoint timeout -> general_settings.pass_through_request_timeo
litellm/passthrough/timeout_utils.py:19
↓ 8 callersFunctionresolve_passthrough_managed_id_provider
Map a pass-through ``custom_llm_provider`` to the provider scope that namespaces passthrough managed object IDs, or ``None`` when the route is not
litellm/llms/base_llm/managed_resources/utils.py:15
↓ 8 callersFunctionresolve_subscription_account_id
(custom_llm_provider: str, litellm_params: Mapping[str, object])
litellm/llms/subscription_accounts.py:35
↓ 8 callersFunctionresourceKeyRead
(ctx context.Context, d *schema.ResourceData, m interface{})
terraform/provider/litellm/resource_key.go:347
↓ 8 callersFunctionresourceLiteLLMBudget
()
terraform/provider/litellm/resource_budget.go:32
↓ 8 callersFunctionresourceLiteLLMCredentialCreate
(d *schema.ResourceData, m interface{})
terraform/provider/litellm/resource_credential_crud.go:108
↓ 8 callersFunctionresourceLiteLLMMCPServer
()
terraform/provider/litellm/resource_mcp_server.go:8
↓ 8 callersFunctionresourceLiteLLMTag
()
terraform/provider/litellm/resource_tag.go:41
↓ 8 callersFunctionresourceLiteLLMUser
()
terraform/provider/litellm/resource_user.go:33
↓ 8 callersFunctionresponse_id
(answer: Answer)
tests/integration/providers/test_chat_completions_tool_search_wire.py:392
↓ 8 callersFunctionresponse_object
(identity: str, status: str, **fields: JsonValue)
tests/integration/_support/responses_stream.py:22
↓ 8 callersMethodresponses_input_to_chat_messages
( input: str | ResponseInputParam | None, )
litellm/responses/utils.py:172
↓ 8 callersFunctionresponses_upstream
(turn_one: Sequence[dict[str, JsonValue]])
tests/integration/_support/responses_replay.py:175
↓ 8 callersMethodrestore
Merge un-committed counts back so the next flush retries them (at-least-once).
litellm/proxy/db/request_error_tracking.py:118
↓ 8 callersMethodresume
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 8 callersFunctionresync_model_deployments_by_ids
(model_ids: tuple[str, ...])
litellm/proxy/common_utils/registry_read_through.py:143
↓ 8 callersFunctionrevoke_refresh_token
RFC 7009 revocation for the gateway's refresh tokens: burn the presented token's ``jti`` and the rotation chain it belongs to, so no rotation of i
litellm/proxy/mcp_server/gateway_dcr_flow.py:1971
↓ 8 callersFunctionrevoke_ui_session_keys
Revoke every UI session key belonging to ``user_id``, except ``keep_hashed_token`` (the caller's own session on a self-service password change
litellm/proxy/management_endpoints/session_endpoints.py:54
↓ 8 callersFunctionroleless_row
(custom_id: str, model: str)
tests/integration/providers/_vertex_batch_rows.py:96
↓ 8 callersFunctionrotate_master_key
Rotate the master key 1. Get the values from the DB - Get models from DB - Get config from DB 2. Decrypt the values
litellm/proxy/management_endpoints/key_management_endpoints.py:5925
↓ 8 callersFunctionroutable_model_name
(model: object, llm_router: "Router | None", custom_llm_provider: object)
litellm/proxy/video_endpoints/utils.py:92
↓ 8 callersFunctionroute
( route_config: SwitchyardRouterConfig, messages: object, *, call_type: str | None = "acomplet
tests/unit/router_strategy/switchyard_router/test_switchyard_router.py:58
↓ 8 callersFunctionrouteSegmentForPathname
(pathname: string)
ui/litellm-dashboard/src/utils/uiHref.ts:19
↓ 8 callersFunctionrouter_arguments
The constructor arguments as passed, by name (positional ones bound to their parameter).
litellm/router.py:211
↓ 8 callersMethodrouting_groups
Routing groups by name (was the ``routing_groups`` attribute).
litellm/router_api.py:1035
↓ 8 callersFunctionrow_to_py
(py: Python<'py>, row: &Row)
litellm-rust/crates/python-bridge/src/router/mod.rs:1120
↓ 8 callersFunctionrs
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 8 callersFunctionrules
(rollout: Rollout)
tests/unit/rust_bridge/test_runtime.py:41
↓ 8 callersMethodrun
()
tests/unit/litellm_core_utils/llm_response_utils/test_convert_dict_to_response.py:2390
↓ 8 callersMethodrun
(self, cmd, *, env=None, cwd=None, timeout=None)
tests/unit/llms/opencode/harness/test_transformation.py:129
↓ 8 callersFunctionrun_turn
(handler: CLIHarnessHandler, ctx: SessionContext, prompt: str)
tests/unit/llms/claude_code/harness/test_transformation.py:213
↓ 8 callersFunctionrun_with
( secrets: Arc<RecordingSecrets>, call: MessagesCall, )
litellm-rust/crates/inference-messages/tests/messages/main.rs:106
↓ 8 callersFunctions1
(e,t=!1)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersFunctionsafe_config_lines
(config: Mapping[str, object], general_settings: Mapping[str, object])
litellm/proxy/bug_report_config.py:187
↓ 8 callersFunctionsafe_set_request_parsed_body
( request: Request | None, parsed_body: dict, )
litellm/proxy/common_utils/http_parsing_utils.py:458
↓ 8 callersFunctionsafeguarded
(body: Mapping[str, JsonValue], safeguards: JsonValue)
tests/integration/providers/_anthropic_safeguards_beta_support.py:232
↓ 8 callersFunctionsanitize_anthropic_tool_use_id
Anthropic requires tool_use_id to match ^[a-zA-Z0-9_-]+$.
litellm/litellm_core_utils/prompt_templates/factory.py:1790
↓ 8 callersMethodsanitize_file_content
Sanitize file content using Prompt Security API. Returns: dict with keys 'action', 'content', 'metadata'
litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py:468
↓ 8 callersFunctionsanitize_openapi_tool_name
Map an OpenAPI operationId / fallback to a provider-safe tool name. Replaces any character outside ``[a-zA-Z0-9_-]`` with ``_`` and caps the
litellm/proxy/mcp_server/openapi_to_mcp_generator.py:62
↓ 8 callersMethodscans
(self, guardrail: str, marker: str)
tests/integration/observability/test_bedrock_converse_stream_post_call_guardrail.py:194
↓ 8 callersFunctionscript
One script call declared on the batch the caller's `NativeSend` picked; `None` without Redis.
litellm-rust/crates/python-bridge/src/redis/store/rate_limits.rs:332
↓ 8 callersMethodscript
(self, response: RoutedResponse | SseResponse)
tests/integration/spend/_background_responses.py:128
↓ 8 callersMethodsearch
( self, query: str, skills: Sequence[LiteLLM_SkillsTable], top_k: int,
litellm/llms/litellm_proxy/skills/skill_search.py:97
↓ 8 callersFunctionsearch_tools
Keyword fallback used when no embedding model is configured: one point per query token found in the tool.
litellm/proxy/mcp_server/tool_search.py:276
↓ 8 callersMethodsecret_location_with_context
( &self, secret_name: &str, context: &HashicorpOperationContext, )
litellm-rust/crates/secrets-hashicorp/src/secret_manager.rs:103
↓ 8 callersMethodseed
(self, *rows: _ProxyObject)
tests/unit/llms/anthropic/messages/conftest.py:59
↓ 8 callersMethodselect
Resolve, filter and pick a deployment without calling it.
litellm-rust/crates/router-core/src/lib.rs:350
↓ 8 callersFunctionselected
The deployment ``select`` picks, or the error it raised.
tests/unit/test_router/core/test_gaps_router_core_crate_picks.py:40
↓ 8 callersFunctionsend
Raw POST returning the unparsed HTTP outcome: status, full body, and the x-litellm-call-id header. For native/passthrough bodies and for calls jud
tests/e2e/e2e_http.py:776
↓ 8 callersFunctionsent_with
(wires: Sequence[Wire], marker: str)
tests/integration/routing/_prompt_cache_pin_support.py:149
↓ 8 callersFunctionserve
(router: Router)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:122
↓ 8 callersMethodserve
(self, router: Router)
tests/unit/llms/anthropic/messages/conftest.py:64
↓ 8 callersFunctionserve_openapi_off_the_event_loop
( app: FastAPI, snapshot: Callable[[], Inputs], build: Callable[[Inputs], OpenAPISchema], )
litellm/proxy/common_utils/openapi_route.py:30
↓ 8 callersMethodserver_exposes_tool
(self, server: MCPServer, tool_name: str)
litellm/proxy/mcp_server/mcp_server_manager.py:3097
↓ 8 callersFunctionserver_owned_wif_fields_present
Server-owned federation or OAuth token-exchange field names set in ``fields``, plus ``api_key`` when it holds an ``oidc/`` secret reference.
litellm/types/router.py:506
↓ 8 callersFunctionservice_span_name
``"{service}.{verb} {target}"`` (``"redis.get llm_response"``) for a known datastore verb, ``"{service}.{verb}"`` (``"redis.pipeline"``) when the
litellm/integrations/otel/model/spans.py:546
↓ 8 callersFunctionsession
( proxy_url: str, key: str, model: str, texts: tuple[str, ...] )
tests/integration/_support/responses_ws_peer.py:163
↓ 8 callersMethodset
( &self, key: &str, value: StoredValue, expire_time: Option<f64>, now:
litellm-rust/crates/cache-disk/src/sqlite.rs:415
↓ 8 callersMethodsetData
(e,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersFunctionsetFieldsValue
(form: McpForm, values: Record<string, unknown>)
ui/litellm-dashboard/src/app/(dashboard)/mcp-servers/_components/mcpFormStore.ts:24
↓ 8 callersFunctionset_access_group_budget
Set or replace the shared budget of an access group. Idempotent. Every key that can reach a model in the group draws from this one budget.
litellm/proxy/management_endpoints/model_access_group_management_endpoints.py:1319
↓ 8 callersMethodset_deployment_model_name
Set the model name for the matched pattern llm deployment E.g.: Case 1: model_name: llmengine/* (can be any regex p
litellm/litellm_core_utils/pattern_match_deployments.py:201
↓ 8 callersMethodset_headers
(self, auth_header: str | None, extra_headers: dict | None)
litellm/llms/vertex_ai/vertex_llm_base.py:1182
↓ 8 callersFunctionset_object_metadata_field
Helper function to set metadata fields that require premium user checks Args: object_data: The team/key/organization/project data ob
litellm/proxy/management_endpoints/common_utils.py:529
↓ 8 callersFunctionsettle
(admission: Option<Admission>, error: Option<&Error>)
litellm-rust/crates/redis-client/src/client.rs:285
↓ 8 callersFunctionsettled_spend
(key: str, expected: float)
tests/integration/providers/_dashscope_video_support.py:137
↓ 8 callersFunctionsetup_for
(ctx: SessionContext)
tests/unit/llms/opencode/harness/test_transformation.py:184
↓ 8 callersMethodshift
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersMethodshould_run_guardrail
(self, data: Mapping[str, object], event_type: GuardrailEventHooks)
litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py:319
↓ 8 callersFunctionshould_store_prompts_and_responses_in_spend_logs
(metadata: Mapping[str, object] | None = None)
litellm/proxy/spend_tracking/spend_tracking_utils.py:2218
↓ 8 callersMethodshould_store_result_in_cache
Helper function to determine if the result should be stored in the cache. Returns: bool: True if the result should be st
litellm/caching/caching_handler.py:1307
↓ 8 callersFunctionshould_strip_caller_authorization
Decide whether the caller's ``Authorization`` header must NOT be forwarded upstream when populating ``extra_headers`` for an MCP server. Cent
litellm/proxy/mcp_server/mcp_server_manager.py:1171
↓ 8 callersFunctionshould_use_emulated_file_search
Return True when there is a file_search tool and the provider can't handle it natively.
litellm/responses/file_search/emulated_handler.py:47
↓ 8 callersFunctionsign_headers
( method: &str, url: &str, body: &[u8], headers: &HeaderMap, scope: SigningScope<'_>, )
litellm-rust/crates/auth-aws/src/aws.rs:570
↓ 8 callersFunctionsignature
AWS SigV4 equations, independent of botocore and LiteLLM's signer; `query` is already canonical.
tests/integration/_support/sigv4.py:26
↓ 8 callersFunctionsplit_complete_sse_frames
Split buffered SSE bytes into ``(complete_frames, unterminated_tail)``.
litellm/proxy/common_utils/sse_keepalive.py:92
↓ 8 callersFunctionsplit_configured_cloud_bucket_name
(bucket_name: str)
litellm/litellm_core_utils/cloud_storage_security.py:104
↓ 8 callersMethodsplit_priority
The request priority and the kwargs without it (was ``split_request_priority``).
litellm/router_api.py:1379
↓ 8 callersFunctionsse_events
(text: str)
tests/integration/_support/responses_stream.py:185
↓ 8 callersFunctionsse_events
(raw: bytes)
tests/integration/_support/safeguards_rig.py:354
↓ 8 callersFunctionsse_frame
(event: str, data: JsonValue)
tests/integration/_support/claude_code.py:657
↓ 8 callersMethodsse_frame
An `event: error` frame, for a stream that fails after its headers went out.
litellm-rust/crates/gateway-inference/src/error.rs:132
↓ 8 callersFunctionstatusline_command
This interpreter, not a bare `python3`: it is the one the apiKeyHelper already depends on.
litellm/proxy/client/cli/commands/claude_settings.py:308
↓ 8 callersMethodstep
( &mut self, step: HookStep<H, T>, continuation: impl FnOnce(HookResume<H, T>) -> Cont
litellm-rust/crates/host-python/src/hooks/chain/adapter.rs:36
↓ 8 callersMethodstop
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersFunctionstop_in_flight_scheduler_jobs
Let in-flight jobs finish for up to finish_timeout_seconds, then stop the scheduler and wait, bounded by cancel_timeout_seconds, for the jobs
litellm/proxy/shutdown/scheduled_jobs.py:43
↓ 8 callersFunctionstop_root_process
(process: subprocess.Popen[bytes])
tests/integration/_support/process.py:152
↓ 8 callersMethodstore_spend_logs_in_redis
Park spend-log rows in Redis so they outlive this pod, dropping the oldest past ``max_rows``.
litellm/proxy/db/db_transaction_queue/redis_update_buffer.py:633
↓ 8 callersFunctionstored_control_options
(litellm_params: Mapping[str, object])
litellm/litellm_core_utils/get_litellm_params.py:144
↓ 8 callersFunctionstored_metadata
(token: str)
tests/integration/authorization/_guardrail_opt_out.py:41
↓ 8 callersFunctionstream_item_items
(item: object, field: str)
litellm/llms/base_llm/guardrail_translation/utils.py:176
↓ 8 callersFunctionstream_through
(host: &RecordingStreamHost)
litellm-rust/crates/inference-messages/tests/messages/stream.rs:143
↓ 8 callersFunctionstrict_tool
(name: str = "lint")
tests/integration/messages_endpoint/test_anthropic_messages_caller_tools_wire.py:33
↓ 8 callersFunctionstrip_callback_config
Return key/team metadata without the slots that carry callback credentials.
litellm/proxy/common_utils/callback_utils.py:715
↓ 8 callersFunctionsuccesses
(core: RouterCore, deployment_id: str)
tests/unit/test_router/core/test_request_scoped_outcomes.py:126
↓ 8 callersMethodsuggest
( self, templates: list, attack_examples: list[str], description: str,
litellm/proxy/management_endpoints/policy_endpoints/ai_policy_suggester.py:59
← previousnext →9,601–9,700 of 202,479, ranked by callers